github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #15319] Gemma 4 Cloud image not accessible #71858

New Issue
Closed
opened 2026-05-05 02:45:40 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-05 02:45:40 -05:00
Owner
Copy Link

Originally created by @jnnngs on GitHub (Apr 4, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15319

What is the issue?

Trying to use the gema 4 cloud model fails with a 404

Tried the following:

gemma4
gemma4:cloud
gemma4:latest
gemma4:latest-cloud

Relevant log output

Failed: HTTP 404: {"error":{"message":"model \"gemma4:cloud\" not found","type":"not_found_error","param":null,"code":null}}

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @jnnngs on GitHub (Apr 4, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15319 ### What is the issue? Trying to use the gema 4 cloud model fails with a 404 Tried the following: gemma4 gemma4:cloud gemma4:latest gemma4:latest-cloud ### Relevant log output ```shell Failed: HTTP 404: {"error":{"message":"model \"gemma4:cloud\" not found","type":"not_found_error","param":null,"code":null}} ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-05 02:45:40 -05:00
GiteaMirror commented 2026-05-05 02:45:44 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 5, 2026):

https://ollama.com/library/gemma4:31b-cloud

<!-- gh-comment-id:4188023125 --> @rick-github commented on GitHub (Apr 5, 2026): https://ollama.com/library/gemma4:31b-cloud
GiteaMirror commented 2026-05-05 02:45:45 -05:00
Author
Owner
Copy Link

@tuangiang1995 commented on GitHub (Apr 5, 2026):

Hi, I also don't think this is working. Is it because I am on 0.17.4? Please see the following logs:

(venv) tuan@dev2:~/Documents/apps/deepclaw$ ollama run gemma4:31b-cloud
Connecting to 'gemma-4:31b' on 'ollama.com' ⚡
>>> hello world
Error: 404 Not Found: model 'gemma-4:31b' not found
(venv) tuan@dev2:~/Documents/apps/deepclaw$ ollama run qwen3.5:cloud
Connecting to 'qwen3.5:397b' on 'ollama.com' ⚡
>>> hello world
Thinking...
Thinking Process:

1.  **Analyze the Request:**
    *   Input: "hello world"
    *   Intent: This is a standard greeting, often used to test systems or initiate conversation.
    *   Expected Output: A friendly greeting in return.

2.  **Determine the appropriate response:**
    *   Keep it simple and friendly.
    *   Acknowledge the greeting.
    *   Offer assistance.

3.  **Drafting the response:**
    *   Option 1: "Hello! How can I help you?"
    *   Option 2: "Hi there! What's on your mind?"
    *   Option 3: "Hello world! How's it going?"

4.  **Selecting the best option:** Option 1 is classic 
and clear.

5.  **Final Polish:** "Hello! How can I assist 
you today?" (Simple, polite, open-ended).

6.  **Final Output Generation:** (Matches the 
selected draft).
...done thinking.

Hello! How can I assist you today?

>>> quit
>>> 
Use Ctrl + d or /bye to exit.
>>> 
Use Ctrl + d or /bye to exit.
>>> 
Use Ctrl + d or /bye to exit.
>>> /bye
(venv) tuan@dev2:~/Documents/apps/deepclaw$ ollama --version
ollama version is 0.17.4
<!-- gh-comment-id:4189183016 --> @tuangiang1995 commented on GitHub (Apr 5, 2026): Hi, I also don't think this is working. Is it because I am on **0.17.4**? Please see the following logs: ```bash (venv) tuan@dev2:~/Documents/apps/deepclaw$ ollama run gemma4:31b-cloud Connecting to 'gemma-4:31b' on 'ollama.com' ⚡ >>> hello world Error: 404 Not Found: model 'gemma-4:31b' not found (venv) tuan@dev2:~/Documents/apps/deepclaw$ ollama run qwen3.5:cloud Connecting to 'qwen3.5:397b' on 'ollama.com' ⚡ >>> hello world Thinking... Thinking Process: 1. **Analyze the Request:** * Input: "hello world" * Intent: This is a standard greeting, often used to test systems or initiate conversation. * Expected Output: A friendly greeting in return. 2. **Determine the appropriate response:** * Keep it simple and friendly. * Acknowledge the greeting. * Offer assistance. 3. **Drafting the response:** * Option 1: "Hello! How can I help you?" * Option 2: "Hi there! What's on your mind?" * Option 3: "Hello world! How's it going?" 4. **Selecting the best option:** Option 1 is classic and clear. 5. **Final Polish:** "Hello! How can I assist you today?" (Simple, polite, open-ended). 6. **Final Output Generation:** (Matches the selected draft). ...done thinking. Hello! How can I assist you today? >>> quit >>> Use Ctrl + d or /bye to exit. >>> Use Ctrl + d or /bye to exit. >>> Use Ctrl + d or /bye to exit. >>> /bye (venv) tuan@dev2:~/Documents/apps/deepclaw$ ollama --version ollama version is 0.17.4 ```
GiteaMirror commented 2026-05-05 02:45:46 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Apr 5, 2026):

Naming conventions for cloud models changed in 0.18.0, you have to upgrade to at least that version to use gemma4:31b-cloud.

<!-- gh-comment-id:4189216666 --> @rick-github commented on GitHub (Apr 5, 2026): Naming conventions for cloud models changed in 0.18.0, you have to upgrade to at least that version to use gemma4:31b-cloud.
GiteaMirror commented 2026-05-05 02:45:48 -05:00
Author
Owner
Copy Link

@tuangiang1995 commented on GitHub (Apr 7, 2026):

Thanks! Upgrading Ollama above version 17 works:

tuan@dev2:~$ ollama run gemma4:31b-cloud
Connecting to 'gemma4:31b-cloud' on 'ollama.com' ⚡
>>> Hello World
Thinking...
The user said "Hello World".
"Hello World" is a classic greeting, often the first program written when learning a new programming language. It's a general greeting.

    *   Acknowledge the greeting.
    *   Match the tone (friendly, helpful).
    *   Provide a few options: a simple greeting, a nod to the programming tradition, or an invitation to ask a question.
"Hello! How can I help you today?" or "Hello! Are we starting a coding project, or just saying hi?"
...done thinking.

Hello! How can I help you today?

>>> /exit
tuan@dev2:~$ ollama --version
ollama version is 0.20.2
<!-- gh-comment-id:4196234345 --> @tuangiang1995 commented on GitHub (Apr 7, 2026): Thanks! Upgrading Ollama above version 17 works: ```bash tuan@dev2:~$ ollama run gemma4:31b-cloud Connecting to 'gemma4:31b-cloud' on 'ollama.com' ⚡ >>> Hello World Thinking... The user said "Hello World". "Hello World" is a classic greeting, often the first program written when learning a new programming language. It's a general greeting. * Acknowledge the greeting. * Match the tone (friendly, helpful). * Provide a few options: a simple greeting, a nod to the programming tradition, or an invitation to ask a question. "Hello! How can I help you today?" or "Hello! Are we starting a coding project, or just saying hi?" ...done thinking. Hello! How can I help you today? >>> /exit tuan@dev2:~$ ollama --version ollama version is 0.20.2 ```
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#71858
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?